Related papers: DCT-Net: Domain-Calibrated Translation for Portrai…
Color and tone stylization strives to enhance unique themes with artistic color and tone adjustments. It has a broad range of applications from professional image postprocessing to photo sharing over social networks. Mainstream photo…
Face sketch synthesis has been widely used in multi-media entertainment and law enforcement. Despite the recent developments in deep neural networks, accurate and realistic face sketch synthesis is still a challenging task due to the…
Meta-learning has been proposed as a framework to address the challenging few-shot learning setting. The key idea is to leverage a large number of similar few-shot tasks in order to learn how to adapt a base-learner to a new task for which…
Domain adaptation of 3D portraits has gained more and more attention. However, the transfer mechanism of existing methods is mainly based on vision or language, which ignores the potential of vision-language combined guidance. In this…
Unsupervised image-to-image translation intends to learn a mapping of an image in a given domain to an analogous image in a different domain, without explicit supervision of the mapping. Few-shot unsupervised image-to-image translation…
Deep Learning has greatly advanced the performance of semantic segmentation, however, its success relies on the availability of large amounts of annotated data for training. Hence, many efforts have been devoted to domain adaptive semantic…
Domain adaptation is one of the prominent strategies for handling both domain shift, that is widely encountered in large-scale land use/land cover map calculation, and the scarcity of pixel-level ground truth that is crucial for supervised…
Few-shot image generation and few-shot image translation are two related tasks, both of which aim to generate new images for an unseen category with only a few images. In this work, we make the first attempt to adapt few-shot image…
Generative adversarial networks has emerged as a defacto standard for image translation problems. To successfully drive such models, one has to rely on additional networks e.g., discriminators and/or perceptual networks. Training these…
The prosperity of deep learning contributes to the rapid progress in scene text detection. Among all the methods with convolutional networks, segmentation-based ones have drawn extensive attention due to their superiority in detecting text…
Medical image segmentation has made significant progress in recent years. Deep learning-based methods are recognized as data-hungry techniques, requiring large amounts of data with manual annotations. However, manual annotation is expensive…
Zero-shot cross-lingual transfer is promising, however has been shown to be sub-optimal, with inferior transfer performance across low-resource languages. In this work, we envision languages as domains for improving zero-shot transfer by…
Deep networks are prone to performance degradation when there is a domain shift between the source (training) data and target (test) data. Recent test-time adaptation methods update batch normalization layers of pre-trained source models…
The goal of unpaired image-to-image translation is to produce an output image reflecting the target domain's style while keeping unrelated contents of the input source image unchanged. However, due to the lack of attention to the content…
Federated Domain Generalization (FDG) aims to collaboratively train a global model across distributed clients that can generalize well on unseen domains. However, existing FDG methods typically struggle with cross-client data heterogeneity…
Domain generalization (DG) has been a hot topic in image recognition, with a goal to train a general model that can perform well on unseen domains. Recently, federated learning (FL), an emerging machine learning paradigm to train a global…
In recent years we have witnessed tremendous progress in unpaired image-to-image translation methods, propelled by the emergence of DNNs and adversarial training strategies. However, most existing methods focus on transfer of style and…
Arbitrary style transfer aims to synthesize a content image with the style of an image to create a third image that has never been seen before. Recent arbitrary style transfer algorithms find it challenging to balance the content structure…
Unsupervised domain adaptation enables to alleviate the need for pixel-wise annotation in the semantic segmentation. One of the most common strategies is to translate images from the source domain to the target domain and then align their…
Typical convolutional networks are trained and conducted on RGB images. However, images are often compressed for memory savings and efficient transmission in real-world applications. In this paper, we explore methods for performing semantic…